A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification (2403.18407v1)
Abstract: Semi-supervised learning (SSL) is a practical challenge in computer vision. Pseudo-label (PL) methods, e.g., FixMatch and FreeMatch, obtain the State Of The Art (SOTA) performances in SSL. These approaches employ a threshold-to-pseudo-label (T2L) process to generate PLs by truncating the confidence scores of unlabeled data predicted by the self-training method. However, self-trained models typically yield biased and high-variance predictions, especially in the scenarios when a little labeled data are supplied. To address this issue, we propose a lightweight channel-based ensemble method to effectively consolidate multiple inferior PLs into the theoretically guaranteed unbiased and low-variance one. Importantly, our approach can be readily extended to any SSL framework, such as FixMatch or FreeMatch. Experimental results demonstrate that our method significantly outperforms state-of-the-art techniques on CIFAR10/100 in terms of effectiveness and efficiency.
- Pseudo-labeling and confirmation bias in deep semi-supervised learning. In 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE, 2020.
- Learning with pseudo-ensembles. Advances in neural information processing systems, 27, 2014.
- Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring. arXiv preprint arXiv:1911.09785, 2019a.
- Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32, 2019b.
- Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp. 702–703, 2020.
- A composite classifier system design: Concepts and methodology. Proceedings of the IEEE, 67(5):708–713, 1979.
- Dozat, T. Incorporating nesterov momentum into adam. 2016.
- Neural network ensembles. IEEE transactions on pattern analysis and machine intelligence, 12(10):993–1001, 1990.
- Exploring balanced feature spaces for representation learning. In International Conference on Learning Representations, 2020.
- Dual student: Breaking the limits of the teacher in semi-supervised learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6728–6736, 2019.
- Learning multiple layers of features from tiny images. 2009.
- Temporal ensembling for semi-supervised learning. arXiv preprint arXiv:1610.02242, 2016.
- Lee, D.-H. et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, pp. 896, 2013.
- Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence, 41(8):1979–1993, 2018.
- A survey of regularization strategies for deep models. Artificial Intelligence Review, 53:3947–3986, 2020.
- Polyak, B. T. Some methods of speeding up the convergence of iteration methods. Ussr computational mathematics and mathematical physics, 4(5):1–17, 1964.
- Bias mimicking: A simple sampling approach for bias mitigation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20311–20320, 2023.
- Regularization with stochastic transformations and perturbations for deep semi-supervised learning. Advances in neural information processing systems, 29, 2016.
- Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608, 2020.
- On the importance of initialization and momentum in deep learning. In International conference on machine learning, pp. 1139–1147. PMLR, 2013.
- Humble teachers teach better students for semi-supervised object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 3132–3141, 2021.
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
- Freematch: Self-adaptive thresholding for semi-supervised learning. arXiv preprint arXiv:2205.07246, 2022.
- Generating unbiased pseudo-labels via a theoretically guaranteed chebyshev constraint to unify semi-supervised classification and regression. arXiv preprint arXiv:2311.01782, 2023.
- Decomposed channel based multi-stream ensemble: Improving consistency targets in semi-supervised 2d pose estimation. Journal of King Saud University-Science, 36(3):103078, 2024.
- Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34, 2021.
- Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. International Journal of Computer Vision, 129(4):1106–1120, 2021.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.